django1/django/utils/encoding.py

225 lines
8.1 KiB
Python

from __future__ import unicode_literals
import codecs
import datetime
from decimal import Decimal
import locale
from django.utils.functional import Promise
from django.utils import six
from django.utils.six.moves.urllib.parse import quote
class DjangoUnicodeDecodeError(UnicodeDecodeError):
def __init__(self, obj, *args):
self.obj = obj
UnicodeDecodeError.__init__(self, *args)
def __str__(self):
original = UnicodeDecodeError.__str__(self)
return '%s. You passed in %r (%s)' % (original, self.obj,
type(self.obj))
def python_2_unicode_compatible(klass):
"""
A decorator that defines __unicode__ and __str__ methods under Python 2.
Under Python 3 it does nothing.
To support Python 2 and 3 with a single code base, define a __str__ method
returning text and apply this decorator to the class.
"""
if six.PY2:
klass.__unicode__ = klass.__str__
klass.__str__ = lambda self: self.__unicode__().encode('utf-8')
return klass
def smart_text(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Returns a text object representing 's' -- unicode on Python 2 and str on
Python 3. Treats bytestrings using the 'encoding' codec.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if isinstance(s, Promise):
# The input is the result of a gettext_lazy() call.
return s
return force_text(s, encoding, strings_only, errors)
def is_protected_type(obj):
"""Determine if the object instance is of a protected type.
Objects of protected types are preserved as-is when passed to
force_text(strings_only=True).
"""
return isinstance(obj, six.integer_types + (type(None), float, Decimal,
datetime.datetime, datetime.date, datetime.time))
def force_text(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Similar to smart_text, except that lazy instances are resolved to
strings, rather than kept as lazy objects.
If strings_only is True, don't convert (some) non-string-like objects.
"""
# Handle the common case first for performance reasons.
if isinstance(s, six.text_type):
return s
if strings_only and is_protected_type(s):
return s
try:
if not isinstance(s, six.string_types):
if six.PY3:
if isinstance(s, bytes):
s = six.text_type(s, encoding, errors)
else:
s = six.text_type(s)
elif hasattr(s, '__unicode__'):
s = six.text_type(s)
else:
s = six.text_type(bytes(s), encoding, errors)
else:
# Note: We use .decode() here, instead of six.text_type(s, encoding,
# errors), so that if s is a SafeBytes, it ends up being a
# SafeText at the end.
s = s.decode(encoding, errors)
except UnicodeDecodeError as e:
if not isinstance(s, Exception):
raise DjangoUnicodeDecodeError(s, *e.args)
else:
# If we get to here, the caller has passed in an Exception
# subclass populated with non-ASCII bytestring data without a
# working unicode method. Try to handle this without raising a
# further exception by individually forcing the exception args
# to unicode.
s = ' '.join([force_text(arg, encoding, strings_only,
errors) for arg in s])
return s
def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Returns a bytestring version of 's', encoded as specified in 'encoding'.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if isinstance(s, Promise):
# The input is the result of a gettext_lazy() call.
return s
return force_bytes(s, encoding, strings_only, errors)
def force_bytes(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Similar to smart_bytes, except that lazy instances are resolved to
strings, rather than kept as lazy objects.
If strings_only is True, don't convert (some) non-string-like objects.
"""
# Handle the common case first for performance reasons.
if isinstance(s, bytes):
if encoding == 'utf-8':
return s
else:
return s.decode('utf-8', errors).encode(encoding, errors)
if strings_only and is_protected_type(s):
return s
if isinstance(s, six.memoryview):
return bytes(s)
if isinstance(s, Promise):
return six.text_type(s).encode(encoding, errors)
if not isinstance(s, six.string_types):
try:
if six.PY3:
return six.text_type(s).encode(encoding)
else:
return bytes(s)
except UnicodeEncodeError:
if isinstance(s, Exception):
# An Exception subclass containing non-ASCII data that doesn't
# know how to print itself properly. We shouldn't raise a
# further exception.
return b' '.join([force_bytes(arg, encoding, strings_only,
errors) for arg in s])
return six.text_type(s).encode(encoding, errors)
else:
return s.encode(encoding, errors)
if six.PY3:
smart_str = smart_text
force_str = force_text
else:
smart_str = smart_bytes
force_str = force_bytes
# backwards compatibility for Python 2
smart_unicode = smart_text
force_unicode = force_text
smart_str.__doc__ = """
Apply smart_text in Python 3 and smart_bytes in Python 2.
This is suitable for writing to sys.stdout (for instance).
"""
force_str.__doc__ = """
Apply force_text in Python 3 and force_bytes in Python 2.
"""
def iri_to_uri(iri):
"""
Convert an Internationalized Resource Identifier (IRI) portion to a URI
portion that is suitable for inclusion in a URL.
This is the algorithm from section 3.1 of RFC 3987. However, since we are
assuming input is either UTF-8 or unicode already, we can simplify things a
little from the full method.
Returns an ASCII string containing the encoded result.
"""
# The list of safe characters here is constructed from the "reserved" and
# "unreserved" characters specified in sections 2.2 and 2.3 of RFC 3986:
# reserved = gen-delims / sub-delims
# gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
# sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
# / "*" / "+" / "," / ";" / "="
# unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
# Of the unreserved characters, urllib.quote already considers all but
# the ~ safe.
# The % character is also added to the list of safe characters here, as the
# end of section 3.1 of RFC 3987 specifically mentions that % must not be
# converted.
if iri is None:
return iri
return quote(force_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~")
def filepath_to_uri(path):
"""Convert a file system path to a URI portion that is suitable for
inclusion in a URL.
We are assuming input is either UTF-8 or unicode already.
This method will encode certain chars that would normally be recognized as
special chars for URIs. Note that this method does not encode the '
character, as it is a valid character within URIs. See
encodeURIComponent() JavaScript function for more details.
Returns an ASCII string containing the encoded result.
"""
if path is None:
return path
# I know about `os.sep` and `os.altsep` but I want to leave
# some flexibility for hardcoding separators.
return quote(force_bytes(path).replace(b"\\", b"/"), safe=b"/~!*()'")
def get_system_encoding():
"""
The encoding of the default system locale but falls back to the given
fallback encoding if the encoding is unsupported by python or could
not be determined. See tickets #10335 and #5846
"""
try:
encoding = locale.getdefaultlocale()[1] or 'ascii'
codecs.lookup(encoding)
except Exception:
encoding = 'ascii'
return encoding
DEFAULT_LOCALE_ENCODING = get_system_encoding()